© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 429
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily triggered by numeric tokens (e.g. literal numbers and decimal figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acés
    0.47
    ríamos
    0.44
    ómago
    0.44
    ávez
    0.44
    ﮈ
    0.44
    ümler
    0.43
    resultado
    0.43
    équilibre
    0.43
    áreas
    0.42
    ໊
    0.42
    POSITIVE LOGITS
     the
    0.80
     this
    0.70
     JPMorgan
    0.67
     The
    0.66
     Volkswagen
    0.65
     Microsoft
    0.64
     Charles
    0.64
     Arizona
    0.64
     Samsung
    0.64
     Toyota
    0.64
    Activations Density 11.818%

    No Known Activations